Low Light Image Denoising Based on Poisson Noise Model and Weighted TV Regularization

Yang, Qi; Jung, Cheolkon; Fu, Qingtao; Song, Hyoseob

doi:10.1109/icip.2018.8451840

Cited by 6 publications

(6 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, as the methods and the related priors are hand-crafted, they have poor adaptability and usually generate unpromising results when being applied to the large-scale testing data. Compound Degradation and RAW Enhancement Some works consider addressing the problem of low-light enhancement as well as its accompanying issues, such as denoising (Lim et al 2015;Liu et al 2015;Li et al 2015;Yang et al 2018) and dehazing . Some methods address the issue with a sequential architecture (Lim et al 2015;Liu et al 2015) while others achieve joint processing with a unified model (Li et al 2015;Yang et al 2018).…”

Section: Multi-exposed Resultsmentioning

confidence: 99%

“…Compound Degradation and RAW Enhancement Some works consider addressing the problem of low-light enhancement as well as its accompanying issues, such as denoising (Lim et al 2015;Liu et al 2015;Li et al 2015;Yang et al 2018) and dehazing . Some methods address the issue with a sequential architecture (Lim et al 2015;Liu et al 2015) while others achieve joint processing with a unified model (Li et al 2015;Yang et al 2018). In general, these methods can achieve good results in their assumed conditions, while a comprehensive model to capture all degradation and handle the corresponding degradation is still absent.…”

Section: Multi-exposed Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Benchmarking Low-Light Image Enhancement and Beyond

et al. 2021

View full text Add to dashboard Cite

In this paper, we present a systematic review and evaluation of existing single-image low-light enhancement algorithms. Besides the commonly used low-level vision oriented evaluations, we additionally consider measuring machine vision performance in the low-light condition via face detection task to explore the potential of joint optimization of high-level and low-level vision enhancement. To this end, we first propose a large-scale low-light image dataset serving both low/high-level vision with diversified scenes and contents as well as complex degradation in real scenarios, called Vision Enhancement in the LOw-Light condition (VE-LOL). Beyond paired low/normal-light images without annotations, we additionally include the analysis resource related to human, i.e. face images in the low-light condition with annotated face bounding boxes. Then, efforts are made on benchmarking from the perspective of both human and machine visions. A rich variety of criteria is used for the low-level vision evaluation, including full-reference, no-reference, and semantic similarity metrics. We also measure the effects of the low-light enhancement on face detection in the low-light condition. State-of-the-art face detection methods are used in the evaluation. Furthermore, with the rich material of VE-LOL, we explore the novel problem of joint low-light enhancement and face detection. We develop an enhanced face detector to apply low-light enhancement and face detection jointly. The features extracted by the enhancement module are fed to the successive layer with the same resolution of the detection module. Thus, these features are intertwined together to unitedly learn useful information across two phases, i.e. enhancement and detection. Experiments on VE-LOL provide a comparison of state-of-the-art low-light enhancement algorithms, point out their limitations, and suggest promising future directions. Our dataset has supported the Track "Face Detection in Low Light Conditions" of CVPR UG2+ Challenge (2019-2020) (http://cvpr2020.ug2challenge.org/).

show abstract

Section: Multi-exposed Resultsmentioning

confidence: 99%

Section: Multi-exposed Resultsmentioning

confidence: 99%

Benchmarking Low-Light Image Enhancement and Beyond

et al. 2021

View full text Add to dashboard Cite

show abstract

“…In this part, we still build the loss function based on Equation 2, however, every sub-loss function has been modified. For the reconstruction loss l rcon and reflectance loss l R in RED-Net, we both adopt the assumption that the noise conforms to the Poisson distribution [39] which is more in line with the real low light image noises. In order to distinguish from the variables in ICE-net, we added the superscript for the variables in RED-Net and the reconstruction loss can be expressed as:…”

Section: Red-netmentioning

confidence: 99%

Self-supervised Low Light Image Enhancement and Denoising

Zhang,

Di,

Zhang

et al. 2021

Preprint

View full text Add to dashboard Cite

This paper proposes a self-supervised low light image enhancement method based on deep learning, which can improve the image contrast and reduce noise at the same time to avoid the blur caused by pre-/post-denoising. The method contains two deep sub-networks, an Image Contrast Enhancement Network (ICE-Net) and a Re-Enhancement and Denoising Network (RED-Net). The ICE-Net takes the low light image as input and produces a contrast enhanced image. The RED-Net takes the result of ICE-Net and the low light image as input, and can re-enhance the low light image and denoise at the same time. Both of the networks can be trained with low light images only, which is achieved by a Maximum Entropy based Retinex (ME-Retinex) model and an assumption that noises are independently distributed. In the ME-Retinex model, a new constraint on the reflectance image is introduced that the maximum channel of the reflectance image conforms to the maximum channel of the low light image and its entropy should be the largest, which converts the decomposition of reflectance and illumination in Retinex model to a non-ill-conditioned problem and allows the ICE-Net to be trained with a self-supervised way. The loss functions of RED-Net are carefully formulated to separate the noises and details during training, and they are based on the idea that, if noises are independently distributed, after the processing of smoothing filters (e.g. mean filter), the gradient of the noise part should be smaller than the gradient of the detail part. It can be proved qualitatively and quantitatively through experiments that the proposed method is efficient.

show abstract

“…Although infrared cameras produce superior image quality under low illumination, ordinary cameras are still typically used for cost considerations. However, video images captured by ordinary cameras in low-illumination environments [1,2] have low signal-to-noise ratios (SNRs). Thus, image change detection must be investigated under noise interference.…”

Section: Introductionmentioning

confidence: 99%

“…Most of them were built on a simple noise model, i.e., the independent and identically distributed additive white Gaussion noise (AWGN). However, in the actual low illuminance monitoring image, there are usually complex random noise [1,2]. In order to improve the accuracy of monitoring image change detection under the condition of low illumination.…”

Section: Introductionmentioning

confidence: 99%

Change Detection in Multitemporal Monitoring Images Under Low Illumination

et al. 2020

View full text Add to dashboard Cite

Video surveillance may involve the simultaneous monitoring of a large number of areas. Realtime automatic change detection of a monitoring area (such as involving the movement of people or vehicles) can reduce risks incurred in negligent manual observation. However, the low signal-to-noise ratio (SNR) of dark environments can significantly corrupt camera images, making it difficult for machine learning surveillance systems to detect small changes in monitored images. In addition, in the absence of changes between two multitemporal monitoring images, sensor noise can lead to false alarms. The objective of this paper is to reduce the effect of sensor noise on change detection of monitored images and the run time of change detection algorithms. For these purposes, we proposed a novel multitemporal monitoring image change detection algorithm based on morphological structure filtering and normalized fusion difference image. First, the random noise in two surveillance images was removed using a multidirectional weighted multiscale series of a morphological filter. Next, two difference images were obtained by using the compression log-ratio operator and the mean ratio operator, and a fusion difference image was obtained by equal-weight fusion of the two difference images. Then, the sigmoid function was used to compress the fusion difference map to obtain a normalized fusion difference image, and a median filter was used to obtain a final difference image. Finally, the k-means clustering algorithm was utilized to obtain the change detection results. The experimental results demonstrate that the proposed method can accurately detect changes in a night monitoring scene in real time. Subjective and objective evaluation of the experimental results demonstrate that the proposed method is superior to reference algorithms in terms of change detection accuracy, time and robustness. INDEX TERMS change detection; morphological structure filtering; normalized fusion difference map; low illumination monitoring image

show abstract

Low Light Image Denoising Based on Poisson Noise Model and Weighted TV Regularization

Cited by 6 publications

References 20 publications

Benchmarking Low-Light Image Enhancement and Beyond

Benchmarking Low-Light Image Enhancement and Beyond

Self-supervised Low Light Image Enhancement and Denoising

Change Detection in Multitemporal Monitoring Images Under Low Illumination

Contact Info

Product

Resources

About